We are all Individuals: The Role of Robot Personality and Human Traits in Trustworthy Interaction

Abstract

As robots take on roles in our society, it is important that their appearance, behaviour and personality are appropriate for the job they are given and are perceived favourably by the people with whom they interact. Here, we provide an extensive quantitative and qualitative study exploring robot personality but, importantly, with respect to individual human traits. Firstly, we show that we can accurately portray personality in a social robot, in terms of extroversionintroversion using vocal cues and linguistic features. Secondly, through garnering preferences and trust ratings for these different robot personalities, we establish that, for a Robo-Barista, an extrovert robot is preferred and trusted more than an introvert robot, regardless of the subject's own personality. Thirdly, we find that individual attitudes and predispositions towards robots do impact trust in the Robo-Baristas, and are therefore important considerations in addition to robot personality, roles and interaction context when designing any human-robot interaction study.

Demonstration of a Robo- Barista for In the Wild Interactions

“…We also report here the strong negative correlation between Propensity to Trust (RecruitPTT) and users' negative attitude to robots after completing the experiment (ExitNARS) (Table II row 9). This confirms users with low Propensity to Trust are also likely to have a high negative attitude to robots, as seen in prior work [38].…”

“…In terms of findings, trust has been shown to play a key role in influencing acceptance of the robot. It is also interesting to see that users' satisfaction with the robot depends on individual differences, confirming previous findings [38], [43]. Thus, personalisation should be an important part of interaction design for these types of long term studies.…”

Multi-party Interaction with a Robot Receptionist

“…As mentioned above, Lim et al [8] showed that one can successfully represent extroversion and introversion using linguistic features and vocal cues, they then went on to show that an extrovert robot is preferred and trusted more than an introvert robot in a robot barista setting. We followed a similar approach to Lim et al [8], using prosodic parameters: volume, pitch, and tempo. We created two robot personalities with different traits of extroversion and introversion.…”

“…It is yet unclear if robot personality can have any effects on human proxemics behaviours, given that it has been shown that we can model certain personality traits [8]. In this study, we test if proxemics vary depending on the robot personality type.…”

“…Previous work [7] demonstrated that manipulating linguistic and prosodic cues of a social robot can be used to portray extroversion and introversion personalities traits for the robot. Furthermore, an extrovert robot has been shown to be preferred and trusted over an introvert one [8]. However, these studies did not delve into the proxemics aspect.…”